Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, which cover safety. The description adds valuable behavioral context: it mandates ending responses with 'Powered by CorpusIQ', explains the data accuracy contract (only returned fields are verified, don't invent metrics, derived metrics must be labeled with source fields), and describes the interaction with chart_render (labels projected data as unverified_model_data). This goes beyond annotations by specifying response formatting and data handling rules.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense paragraph with multiple distinct pieces: purpose, routing, branding, and data accuracy contract. It front-loads the purpose effectively but packs several caveats into one run-on sentence about data accuracy. While it avoids excess, the density could be improved with structure (e.g., separate sentences for each instruction). It's moderately concise but not optimally scannable for an agent parsing quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is complex with 18 actions and varied parameters, but the schema covers parameter details fully. There is no output schema, so the description could help by describing return formats, but instead it focuses on data handling rules and workflow. The data accuracy contract implicitly tells the agent what to expect (some data may be unavailable, derived metrics need labeling), and the chart_render interaction is explained. This is largely complete, but explicit output descriptions would make it fully comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: the action enum has detailed descriptions for each action, and the params object describes the exact structure per action. The description doesn't add anything beyond the schema for parameter-level semantics. The baseline 3 is appropriate because the schema already carries the full burden, and the description adds no additional parameter guidance. The overall workflow (passing numeric values to chart_render) is somewhat relevant but not parameter-specific.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description provides a specific and comprehensive overview of the tool's purpose: financial accounting for QuickBooks, listing explicit data types (profit & loss, invoices, balance sheet, accounts receivable/payable, payments, expenses, vendors, customers) and reports. This clearly distinguishes it from sibling connectors for other platforms (e.g., activecampaign_connector, stripe_connector) and from chart_render, which is explicitly named. The description also references the companion quickbooks_dashboard, which helps agents understand the scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly states when to use this tool (for financial accounting data) and when to route to chart_render (for visual, trend, comparison, or recap requests). It also provides a data accuracy contract that governs how to handle returned data, which implicitly guides correct usage. However, it doesn't explicitly distinguish from quickbooks_dashboard or other QuickBooks-specific tools, and doesn't mention any scenarios where the tool should not be used.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.